Swe Bench Verified

dataset_info:
features:

• name: repo
  dtype: string
• name: instance_id
  dtype: string
• name: base_commit
  dtype: string
• name: patch
  dtype: string
• name: test_patch
  dtype: string
• name: problem_statement
  dtype: string
• name: hints_text
  dtype: string
• name: created_at
  dtype: string
• name: version
  dtype: string
• name: FAIL_TO_PASS
  dtype: string
• name: PASS_TO_PASS
  dtype: string
• name: environment_setup_commit
  dtype: string
• name: difficulty
  dtype: string
  splits:
• name: test
  num_bytes: 7779763
  num_examples: 500
  download_size: 2096679
  dataset_size: 7779763
  configs:
• config_name: default
  data_files:
  • split: test
    path: data/test-*

Dataset Summary

SWE-bench Verified is a subset of 500 samples from the SWE-bench test set, which have been human-validated for quality. SWE-bench is a dataset that tests systems’ ability to solve GitHub issues automatically. See this post for more details on the human-validation process.

The dataset collects 500 test Issue-Pull Request pairs from popular Python repositories. Evaluation is performed by unit test verification using post-PR behavior as the reference solution.

The original SWE-bench dataset was released as part of SWE-bench: Can Language Models Resolve Real-World GitHub Issues?

Want to run inference now?
This dataset only contains the problem_statement (i.e. issue text) and the base_commit which represents the state of the codebase before the issue has been resolved. If you want to run inference using the "Oracle" or BM25 retrieval settings mentioned in the paper, consider the following datasets.

princeton-nlp/SWE-bench_Lite_oracle

princeton-nlp/SWE-bench_Lite_bm25_13K

princeton-nlp/SWE-bench_Lite_bm25_27K

Supported Tasks and Leaderboards
SWE-bench proposes a new task: issue resolution provided a full repository and GitHub issue. The leaderboard can be found at www.swebench.com

Languages
The text of the dataset is primarily English, but we make no effort to filter or otherwise clean based on language type.

Dataset Structure

An example of a SWE-bench datum is as follows:

instance_id: (str) - A formatted instance identifier, usually as repo_owner__repo_name-PR-number.
patch: (str) - The gold patch, the patch generated by the PR (minus test-related code), that resolved the issue.
repo: (str) - The repository owner/name identifier from GitHub.
base_commit: (str) - The commit hash of the repository representing the HEAD of the repository before the solution PR is applied.
hints_text: (str) - Comments made on the issue prior to the creation of the solution PR’s first commit creation date.
created_at: (str) - The creation date of the pull request.
test_patch: (str) - A test-file patch that was contributed by the solution PR.
problem_statement: (str) - The issue title and body.
version: (str) - Installation version to use for running evaluation.
environment_setup_commit: (str) - commit hash to use for environment setup and installation.
FAIL_TO_PASS: (str) - A json list of strings that represent the set of tests resolved by the PR and tied to the issue resolution.
PASS_TO_PASS: (str) - A json list of strings that represent tests that should pass before and after the PR application.